The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from GitHub issues, which could be used to deliver malicious instructions to the agent.
Ingestion points: The skill instructions in SKILL.md direct the agent to fetch the title, body, and comments of an issue using the gh issue view command.
Boundary markers: There are no explicit instructions or delimiters defined to help the agent distinguish between legitimate issue descriptions and potentially malicious instructions embedded in the external data.
Capability inventory: The skill grants the agent capabilities to modify the local source code, execute application tests, and interact with the veris CLI tool.
Sanitization: No sanitization, validation, or filtering of the content retrieved from GitHub is specified before the agent processes the data.

fix